Update web.py

web.py

@@ -431,10 +431,10 @@ def web_data():
         """),
         P("We directly read WARC files instead of WET files and extracted text using Trafilatura. Similar to RefinedWeb, we avoid using Machine Learning (ML)-based metrics for filtering documents to prevent bias introduced by ML models. Importantly, we apply global deduplication across the entire dataset, whereas previous works only use local deduplication. Note that although The Pile also employed global deduplication on its web data (Pile-CC), this accounted for just 0.6\% of 74 snapshots."),
 
-       # Details(
-       #         Summary("Text Extraction Examples"),
-       #         DV2("data/sample_wet.json", "data/sample_warc.json", 3),
-       #     ),
+        Details(
+                Summary("Text Extraction Examples"),
+                DV2("data/sample_wet.json", "data/sample_warc.json", 3),
+            ),
         #DV2("data/sample_wet.json", "data/sample_warc.json", 3),
         
         H4("1.2 Language Identification"),
@@ -443,12 +443,9 @@ def web_data():
         This step removes over 60% of the whole data.
         """),
     
-        Details(
-                Summary("Sample documents that are classified as non-English"),
-                DV("data/sample_non_en.json", 3),
-            ),
+       
              
-        #DV("data/sample_non_en.json", 3, "Sample documents that are classified as non-English"),
+        DV("data/sample_non_en.json", 3, "Sample documents that are classified as non-English"),
             
         
         DV("data/sample_en_low.json", 3, "Sample documents that are classified as English but with score less than 0.65"),